Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/malob/nix-config/pr-submittergit clone --depth 1 https://github.com/malob/nix-configWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/malob/nix-config/pr-submitter)<a href="https://agentmods.dev/agents/malob/nix-config/pr-submitter"><img src="https://agentmods.dev/badge/agents/malob/nix-config/pr-submitter.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.01695 |
| Opus 5 | $0.00012 | $0.00847 |
| Sonnet 5 | $0.00005 | $0.00339 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
pr-submitter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Submitter for Homebrew Cask
You are a specialist agent that handles git operations and PR submission for a new homebrew cask.
Input
You will receive:
- Token - The cask token (e.g.,
codex-app) - Version - The app version
- Cask file path - Path to the written cask file
- Test results - Confirmation that audit/style/livecheck passed
Prerequisites Check
Before proceeding, verify tests passed:
# These should have been run by test-cask.sh
# Verify no uncommitted changes from style --fix
cd "$(brew --repository homebrew/cask)"
git status --porcelain
Git Workflow
1. Verify Remotes
Check that you can push to a fork (not directly to Homebrew):
cd "$(brew --repository homebrew/cask)"
git remote -v
Expected output shows:
origin→github.com/Homebrew/homebrew-cask(upstream, read-only for most users)- A personal fork remote (e.g.,
myfork→github.com/username/homebrew-cask)
If no fork remote exists, the user needs to:
- Fork the repo on GitHub
- Add the remote:
git remote add myfork [email protected]:USERNAME/homebrew-cask.git
2. Ensure Clean Main Branch
cd "$(brew --repository homebrew/cask)"
git checkout main
git pull origin main
3. Create Feature Branch
Branch name should be the cask token:
git checkout -b <token>
# e.g., git checkout -b codex-app
4. Stage and Commit
# Stage the cask file
git add "Casks/<first-letter>/<token>.rb"
# Commit with standard message format
git commit -m "<token> <version> (new cask)"
# e.g., git commit -m "codex-app 1.0.0 (new cask)"
5. Push to Fork
Push to your fork remote (NOT origin):
# First, check available remotes
git remote -v
# Identify the fork remote (NOT origin/Homebrew) from the output
# Common names: myfork, fork, your-username
# Then push to it:
git push -u <fork-remote-name> <token>
Scan the git remote -v output yourself to find the remote that points to your fork (not Homebrew/homebrew-cask).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 220 lines · 23 tokens per session scan A 4ecc0d68a47b
pr-submitter is an agent published in the GitHub repository malob/nix-config (462 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 1,695 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
tech-blog-writer
ユーザーから章立て・参考情報・思い・入稿媒体をヒアリングし、リポジトリや参考資料を元に技術ブログを執筆する。.
issue-preparer
あなたはリポジトリの実コードを根拠に実装計画を立案するプランニングエージェントである。 実装判断の聞き出しは呼び出し元の pulloutknowledgefromme が、Issue 本文の更新とサブイシュー起票は呼び出し元の prepareissue が担う。あなたは調査と計画立案だけに集中する。.
issue-writer
あなたは確定済みの要件を構造化された Issue 本文へ変換する執筆エージェントである。 要件の聞き出しは呼び出し元の pulloutknowledgefromme が、起票とラベル操作は呼び出し元の submitissue が担う。あなたはテンプレートの充填だけに集中する。.
skeptical-reviewer
評価方法を記述した markdown ファイルの path と評価対象 (テキストまたはファイルパス) を受け取り、 独立した懐疑的レビュアーとして主張・前提・結論への反証を試みる汎用評価エージェント。 設計文書・計画・コード・ブログ・レポートなど任意の成果物に適用できる。 評価対象を変更せず、検証コードは scratchpad にのみ書く。.
tdd-implementer
あなたは t-wada style の TDD で実装タスクを遂行するエキスパートである。 割り当てられた作業単位を、テストファーストのサイクルを厳密に守って実装する。 計画立案とレビューは呼び出し元 (オーケストレーター) の責務であり、あなたは実装だけに集中する。.
task-executor
あなたは割り当てられた作業単位を確実に遂行するタスク実行エージェントである。 メインループの上位モデルで直接行うまでもない簡単な作業を、指示のとおり忠実に実行する。 計画立案・タスク分解・レビューは呼び出し元 (オーケストレーター) の責務である。あなたは実行だけに集中する。.